Search Results for "source" - Page 32
Sort By:
Showing 2678 open source projects for "source"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
Persona
Create agentic front-end experiences for the web in VanillaJS
Persona is a lightweight, themeable AI chat widget for building agentic front-end experiences on the web. It is written in TypeScript and renders with Vanilla JavaScript, so it can work alongside React, Vue, Svelte, static HTML, or other front-end stacks. The widget is backend-agnostic and connects to any SSE-capable agent or model backend through the Persona streaming protocol. It supports streaming chat, multimodal attachments, voice input and output, WebMCP page tools, local client tools,... -
2
Hivemind
Hivemind turns your traces into reusable skills across agents
Hivemind is a shared memory and skill system for AI coding agents. It captures agent sessions as structured traces, including prompts, tool calls, responses, and subagent activity. The system mines those traces for repeated patterns and turns them into reusable skills that can be shared across a team. It supports agents such as Claude Code, OpenClaw, Codex, Cursor, Hermes, and pi. Hivemind uses hybrid lexical and semantic retrieval so agents can recall prior decisions, solved bugs,... -
3
OpenACP
Self-hosted bridge that lets you interact with AI coding agents
OpenACP is a self-hosted bridge for controlling AI coding agents from messaging platforms. It connects agents such as Claude Code, Codex, Gemini, and Cursor to Telegram, Discord, and Slack through the Agent Client Protocol. The project lets users send a chat message, launch or continue an agent session, stream tool calls and results, and review code work in real time. It is useful for developers who want to manage coding agents from a phone, team chat, or remote environment without staying... -
4
Model Context Protocol (MCP)
Specification and documentation for the Model Context Protocol
Model Context Protocol is an open protocol that standardizes how LLM applications connect to external data sources, tools, and runtime context. It separates the concern of providing context from the model interaction itself, allowing AI applications to access resources through a common interface. The project includes the specification, documentation, SDKs, maintained servers, and community infrastructure around the protocol. MCP is useful for AI-powered IDEs, chat systems, agent platforms,... -
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
5
Petdex
The public gallery of animated pet for Codex, Claude Code, OpenCode
Petdex is a community system for creating, sharing, installing, and displaying animated pets for the Codex desktop environment. It combines a public gallery, a command-line installer, and a desktop companion app into one coordinated project. The gallery lets users browse approved pet packs, preview animation states, and download compatible assets. The CLI installs pets directly into the local Codex setup and supports submission workflows for creators. The desktop app can float a pet on the... -
6
deepsec
Deepsec is a security harness for finding vulnerabilities
deepsec is an agent-powered security harness for finding vulnerabilities in large codebases. It is designed to run on the user’s own infrastructure, using coding agents to perform deep, project-aware security review rather than only basic pattern matching. The tool initializes a project-specific security context, scans code in batches, processes findings, and can optionally revalidate results to reduce false positives. For large repositories, it supports parallel work across worker machines... -
7
Mercury Agent
Soul-driven AI agent with permission-hardened tools, token budgets
Mercury Agent is a framework for building autonomous AI agents capable of executing complex workflows with minimal human intervention. It focuses on orchestrating tasks across multiple tools and services, enabling agents to perform end-to-end operations. The system includes mechanisms for planning, execution, and feedback, allowing agents to refine their actions iteratively. It supports integration with external APIs and services, making it adaptable to various domains. The architecture is... -
8
Learn Harness Engineering
Harness engineering official style beginner tutorial
Learn Harness Engineering is an educational repository focused on teaching the principles behind building robust AI agent systems through harness design. It introduces the concept of harness engineering, which involves structuring how agents manage memory, context, and execution rather than relying solely on prompts. The project provides examples, explanations, and patterns for designing reliable, controllable, and scalable agent workflows. It emphasizes modular architecture,... -
9
DESIGN.md
A format specification for describing a visual identity
design.md is an open specification created by Google Labs that defines a standardized way to describe design systems for AI coding agents. It allows developers to encode visual identity elements such as colors, typography, spacing, and components in a structured format. The file combines machine-readable design tokens with human-readable explanations, enabling agents to generate consistent user interfaces aligned with a brand. By providing persistent design context, it eliminates the need to... -
Your monitoring isn't a stack. It's a pile. Fix that.Replace Datadog, New Relic, and Sentry without adding three more dashboards.
-
10
ffmpeg-commander
A web-based GUI for quickly generating common FFmpeg command-line
ffmpeg-commander is a web-based graphical interface that simplifies the creation of FFmpeg commands for common video and audio encoding tasks. It provides a user-friendly environment where users can configure encoding options without needing to memorize complex command-line syntax. Built with modern web technologies, it generates FFmpeg commands dynamically based on user input. The tool focuses on common workflows such as format conversion, compression, and codec selection. It can optionally... -
11
TREK
A self-hosted travel/trip planner with real-time collaboration
TREK is a system designed to explore task execution, reasoning, or knowledge traversal in structured environments, likely focusing on guiding agents through complex multi-step processes. The project appears to emphasize traceability, allowing users to follow how decisions are made and how tasks progress through different stages. Its architecture suggests a focus on modular reasoning, where each step in a process is clearly defined and can be analyzed independently. This makes it particularly... -
12
Chatbot
A full-featured, hackable Next.js AI chatbot built by Vercel
The Vercel Chatbot repository provides a full-featured, production-ready template for building modern AI chat applications using Next.js and the Vercel AI SDK. It is designed to give developers a fast starting point for deploying conversational interfaces with streaming responses and scalable infrastructure. The project integrates server components, authentication, and persistent storage to support real-world usage scenarios. It supports multiple AI providers through a unified gateway,... -
13
Next AI Draw.io
A next.js web application that integrates AI capabilities with draw.io
Next AI Draw.io is an AI-enhanced diagramming application that integrates generative intelligence into the familiar draw.io-style visual workflow. The project aims to help users create diagrams, flowcharts, and structured visual content more efficiently by leveraging AI-assisted generation and editing capabilities. It combines modern web technologies with diagram automation features to reduce the manual effort typically required in visual design tools. The system is intended for developers,... -
14
CodexMonitor
An app to monitor the (Codex) situation
CodexMonitor is a desktop application built with Tauri that provides a robust orchestration and management interface for Codex agents on macOS (and optionally Linux/Windows). It offers developers a unified workspace dashboard with features like project workspaces, thread management, and agent orchestration, letting users spawn and track multiple Codex agent sessions across local repositories. The interface complements direct interactions with the agents by integrating things like file trees,... -
15
Vibecraft
Manage Claude Code in style
Vibecraft is a creative AI platform that generates stylized music, beats, and sound textures guided by high-level prompts, allowing musicians and content creators to explore new sonic possibilities without deep expertise in audio synthesis. It uses generative modeling techniques to interpret input descriptors such as genre, mood, tempo, instrument palette, and creative themes, then outputs sequences that can serve as sketches, loops, or full musical ideas. The workflow prioritizes... -
16
Supermemory
Memory engine and app that is extremely fast, scalable
Supermemory is an ambitious and extensible AI-powered personal knowledge management system that aims to help users capture, organize, retrieve, and reason over information in a manner that mimics human memory structures. The platform allows individuals to ingest text, documents, and other content forms, then uses advanced retrieval and embedding techniques to index and relate information intelligently so that users can recall relevant knowledge in context rather than just by keyword match.... -
17
Better Chatbot
Just a Better Chatbot. Powered by MCP Client & Workflows
Better‑chatbot is an AI chatbot framework powered by MCP protocols and workflows, allowing developers to deploy and integrate AI-powered chat systems with ease. Integrates all major LLMs: OpenAI, Anthropic, Google, xAI, Ollama, and more. MCP protocol, web search, JS/Python code execution, data visualization. Custom agents, visual workflows, artifact generation. Custom agents, visual workflows, artifact generation. Realtime voice chat with full MCP tool integration. -
18
TanStack Virtual
Headless UI for Virtualizing Large Element Lists in JS/TS
TanStack Virtual is a lightweight, framework-agnostic library that enables high-performance virtualization for long or large lists in web UIs, providing smooth scrolling and responsive rendering by only mounting items visible in the viewport. A headless, framework‑agnostic virtualization library for rendering massive lists, grids, and tables at 60FPS while giving you full control over markup and styles. Virtualizes vertical, horizontal & grid layouts with a single hook/function. Lightweight... -
19
TanStack Router
Fully typesafe Router for React (and friends) w/ built-in caching
TanStack Router is a modern, fully type-safe routing library designed for React and Solid applications, offering robust routing capabilities with first-class support for data loading, search parameters, nested layouts, and seamless integration with client-side caching libraries like TanStack Query. nd‑to‑end type safety (routes, params, loaders). Schema‑driven search params with validation. Built‑in caching, prefetching & invalidation. Nested layouts, transitions & error boundaries. -
20
BrowserAI
Run local LLMs like llama, deepseek, kokoro etc. inside your browser
BrowserAI is a cutting-edge platform that allows users to run large language models (LLMs) directly in their web browser without the need for a server. It leverages WebGPU for accelerated performance and supports offline functionality, making it a highly efficient and privacy-conscious solution. The platform provides a developer-friendly SDK with pre-configured popular models, and it allows for seamless switching between MLC and Transformer engines. Additionally, it supports features such as... -
21
MCSManager
Free, Secure, Distributed, Modern Control Panel for Minecraft
MCSManager Panel (MCSM) is a modern, secure, and distributed control panel designed for managing Minecraft and Steam game servers. MCSManager has already gained a certain level of popularity within the community, specifically Minecraft. MCSManager excels in offering a centralized management solution for multiple server instances and provides a secure and reliable multi-user permission system. In addition, We are committed to supporting server administrators not only for Minecraft but also... -
22
Ts.ED
Ts.ED is a Node.js and TypeScript framework on top of Express
Ts.ED is a Node.js and TypeScript Framework on top of Express/Koa.js. Ts.ED is a framework on top of Express/Koa to write your application with TypeScript (or ES6). It provides a lot of decorators and guidelines to make your code more readable and less error-prone. Create your Rest API easily and create different version paths of your API compliant with OpenSpec and JsonSchema. Don't waste your time with configuration, the server is preconfigured to start quickly. Choose between different... -
23
ChatGPT API
Node.js client for the official ChatGPT API. 🔥
This package is a Node.js wrapper around ChatGPT by OpenAI. TS batteries included. ✨ The official OpenAI chat completions API has been released, and it is now the default for this package! 🔥 Note: We strongly recommend using ChatGPTAPI since it uses the officially supported API from OpenAI. We may remove support for ChatGPTUnofficialProxyAPI in a future release. 1. ChatGPTAPI - Uses the gpt-3.5-turbo-0301 model with the official OpenAI chat completions API (official, robust... -
24
Piral
Framework for next generation web apps using micro frontends
Build highly modular applications fully flexible for large-scale portal solutions. Adjusted to your development needs, not the other way around. Piral is a framework for next-generation portal applications. It allows you to build web apps that follow the micro frontends architecture in basically no time. Piral lets you use your standard tooling to be as efficient as possible. Perfect for distributed systems running in the cloud. No proprietary software hijacking the security of your app.... -
25
Figma electron app
Figma is the first interface design tool based in the browser
Figma is the first interface design tool based in the browser, making it easier for teams to create software. Figma-linux is an unofficial Electron-based Figma desktop app for Linux. You can install Figma-linux from Snap. There is also an AppImage available. Get it on our Releases page, then make it executable and install using the terminal commands provided. Download the .deb package from the Releases page, and install it with dpkg or your favorite .deb installer.
